{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor — Robots.txt & Sitemap.xml Parser", "description": "Extracts the URLs a website lists in its XML sitemaps (sitemap indexes, gzip and text sitemaps, robots.txt discovery), up to your Max URLs cap, with filters and a clear per-site report.", "version": "0.4", "x-build-id": "tHHIerGSCXxmR7OMn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tarnlight~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tarnlight-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tarnlight~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-tarnlight-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tarnlight~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-tarnlight-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Site homepages (e.g. https://example.com) or direct sitemap URLs (e.g. https://example.com/sitemap.xml). A homepage/site URL triggers robots.txt Sitemap: discovery and common-path probing. A direct sitemap URL is fetched by itself, and ONLY that file (plus its sitemap-index children, if any) -- it never expands into a whole-site discovery, so you're never charged for URLs you didn't ask for.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Max URLs", "minimum": 0, "type": "integer", "description": "Stop once this many URLs have been written to the dataset across all start URLs (0 = unlimited -- can run up an unbounded bill on a large site; set a cap unless you really want everything). Each URL costs $0.001, so the default of 5,000 caps a run at about $5 (plus the $0.005 start fee).", "default": 5000 }, "includePatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Only keep extracted URLs matching at least one of these regular expressions. Leave empty to keep all.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop extracted URLs matching any of these regular expressions.", "default": [], "items": { "type": "string" } }, "modifiedSince": { "title": "Modified since", "type": "string", "description": "ISO date (e.g. 2025-01-01). Only keep URLs whose is on or after this date. See 'Keep URLs without lastmod' for URLs missing a lastmod value." }, "keepUrlsWithoutLastmod": { "title": "Keep URLs without lastmod", "type": "boolean", "description": "Only matters when 'Modified since' is set. Off (default): URLs with no usable (missing, or a placeholder like 0000-00-00) are dropped and not charged, so you only pay for URLs known to match your date. On: keep them too (their date is unknown).", "default": false }, "discoverFromRobots": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "For a homepage/site-root start URL: use robots.txt's 'Sitemap:' lines for discovery (in addition to any common-path probing). Has no effect on a direct sitemap URL, which is always fetched by itself. robots.txt is always fetched and its Disallow rules are always honoured regardless of this setting; it only controls whether declared sitemaps are added to the discovery list.", "default": true }, "tryCommonPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "For a homepage/site-root start URL: also probe well-known paths (/sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml, /sitemap.xml.gz, /sitemap.txt) at its origin, regardless of what robots.txt declares (some sites keep a stale legacy sitemap at a common path alongside a different declared one). Has no effect on a direct sitemap URL, which is always fetched by itself.", "default": true }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Include entries for each URL in the output.", "default": false }, "includeImages": { "title": "Include image sitemap data", "type": "boolean", "description": "Include image count (and image URLs) from entries in the output.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of sitemap/robots.txt requests in flight at once, across all sites.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Timeout for each HTTP request to a robots.txt or sitemap file.", "default": 30 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }